Search papers, labs, and topics across Lattice.
3
0
6
2
Spotting scams before they fully unfold is now possible: ORACLE anticipates smartphone fraud from streaming app usage by distilling knowledge from anti-scam reflections, enabling early warnings with fewer false positives.
Diffusion models can be made more efficient and produce better outputs by dynamically allocating compute based on a learned "difficulty" signature, without any retraining.
A 2B parameter model trained on a new 1.1M dataset can now forecast remote sensing scenes better than Gemini-2.5-Flash Image, suggesting that task-specific training data and methods can beat sheer scale.
